Nano Banana 2.1 on Google AI Studio

Gemini 3.1 · Google DeepMind

Serverless

Last refreshed 2026-10-07. Next refresh: weekly.

Why use Nano Banana 2.1 on Google AI Studio?

Google AI Studio offers Nano Banana 2.1 with pay-as-you-go pricing at $1.50/1M input tokens. Google AI Studio is a model prototyping environment and API access point for Gemini models, offering an inference playground for developers to test and build AI applications.

Compare Nano Banana 2.1 across 3 providers to find the best fit for your use case
Input / 1M
$1.50
Output / 1M
$7.50
Cache
Not sourced
Batch
-50% · in $0.75 / out $3.75

Setup recipe

Python + curl
Install
pip install google-genai
Auth
export GOOGLE_API_KEY=...
Call
import os
from google import genai
client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
response = client.models.generate_content(
Model ID
gemini-nano-banana-2.1

Request example

import os
from google import genai

client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
response = client.models.generate_content(
    model="gemini-nano-banana-2.1",
    contents="Hello"
)
print(response.text)

Gotchas

  • Use the model name directly, e.g. "gemini-2.0-flash", "gemini-1.5-pro", or "gemini-2.5-pro-preview-05-06".
  • The examples expect GOOGLE_API_KEY; rename it only if your application config maps the new variable.

Compare Nano Banana 2.1 Across Providers

ProviderInput (per 1M)Output (per 1M)
Google AI Studio$1.50$7.50
OpenRouter$1.50$7.50
Vercel AI Gateway$1.50$7.50

Pricing

TypePrice (per 1M)
Input tokens$1.50
Output tokens$7.50

Capabilities

VisionMultimodalReasoningBatch API

About Nano Banana 2.1

Nano Banana 2.1 (API id gemini-nano-banana-2.1, GA 6 October 2026) is Google's high-efficiency Gemini image generation and conversational editing model, succeeding Nano Banana 2 (gemini-3.1-flash-image). First-party Gemini API docs: text/image/video/PDF in, image+text out; 131,072 input / 32,768 output tokens; Thinking levels minimal/medium/high; Google Web and Image Search grounding; up to 14 reference images; 1K/2K/4K output (default 1K); Batch API supported; caching not supported. DeepMind model card (Published 6 October 2026) says it is based on Gemini 3.6 Flash.

Get Started